@inproceedings{humayoun-yu-2016-analyzing,
title = "Analyzing Pre-processing Settings for {U}rdu Single-document Extractive Summarization",
author = "Humayoun, Muhammad and
Yu, Hwanjo",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1585",
pages = "3686--3693",
abstract = "Preprocessing is a preliminary step in many fields including IR and NLP. The effect of basic preprocessing settings on English for text summarization is well-studied. However, there is no such effort found for the Urdu language (with the best of our knowledge). In this study, we analyze the effect of basic preprocessing settings for single-document text summarization for Urdu, on a benchmark corpus using various experiments. The analysis is performed using the state-of-the-art algorithms for extractive summarization and the effect of stopword removal, lemmatization, and stemming is analyzed. Results showed that these pre-processing settings improve the results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="humayoun-yu-2016-analyzing">
<titleInfo>
<title>Analyzing Pre-processing Settings for Urdu Single-document Extractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Humayoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwanjo</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Preprocessing is a preliminary step in many fields including IR and NLP. The effect of basic preprocessing settings on English for text summarization is well-studied. However, there is no such effort found for the Urdu language (with the best of our knowledge). In this study, we analyze the effect of basic preprocessing settings for single-document text summarization for Urdu, on a benchmark corpus using various experiments. The analysis is performed using the state-of-the-art algorithms for extractive summarization and the effect of stopword removal, lemmatization, and stemming is analyzed. Results showed that these pre-processing settings improve the results.</abstract>
<identifier type="citekey">humayoun-yu-2016-analyzing</identifier>
<location>
<url>https://aclanthology.org/L16-1585</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3686</start>
<end>3693</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Pre-processing Settings for Urdu Single-document Extractive Summarization
%A Humayoun, Muhammad
%A Yu, Hwanjo
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F humayoun-yu-2016-analyzing
%X Preprocessing is a preliminary step in many fields including IR and NLP. The effect of basic preprocessing settings on English for text summarization is well-studied. However, there is no such effort found for the Urdu language (with the best of our knowledge). In this study, we analyze the effect of basic preprocessing settings for single-document text summarization for Urdu, on a benchmark corpus using various experiments. The analysis is performed using the state-of-the-art algorithms for extractive summarization and the effect of stopword removal, lemmatization, and stemming is analyzed. Results showed that these pre-processing settings improve the results.
%U https://aclanthology.org/L16-1585
%P 3686-3693
Markdown (Informal)
[Analyzing Pre-processing Settings for Urdu Single-document Extractive Summarization](https://aclanthology.org/L16-1585) (Humayoun & Yu, LREC 2016)
ACL